Poster
in
Workshop: First Workshop on LLM Persona Modeling

Interaction as Intelligence: Deep Research With Human-AI Partnership

Lyumanshan Ye ⋅ Xiaojie Cai ⋅ Xinkai Wang ⋅ Junfei Wang ⋅ Xiangkun Hu ⋅ Jiadi Su ⋅ Yang Nan ⋅ Sihan Wang ⋅ Bohan Zhang ⋅ Xiaoze Fan ⋅ Luo Jinbin ⋅ Yuxiang Zheng ⋅ Tianze Xu ⋅ Dayuan Fu ⋅ Yunze Wu ⋅ Pengrui Lu ⋅ Zengzhi Wang ⋅ Yiwei Qin ⋅ Zhen Huang ⋅ Yan Ma ⋅ Zhulin Hu ⋅ Haoyang Zou ⋅ Tiantian Mi ⋅ Yixin Ye ⋅ Ethan Chern ⋅ Fan Zhou ⋅ Pengfei Liu

Project Page [ OpenReview]

Abstract

Despite advances in large language models(LLMs), current systems for deep research are limited by an asynchronous, ``input-wait-output" interaction paradigm. This model creates a critical disconnect between human intent and AI execution, leading to error propagation and an inability to dynamically course-correct during complex problem-solving. %We propose that a more effective form of human-AI partnership requires a shift from passive command-giving to cognitive oversight, where humans actively guide and intervene in the AI's thinking process. This perspective treats interaction as a core component of intelligence, rather than a peripheral interface. We introduce Deep Cognition, a system designed to enable this paradigm through three technical pillars: transparent and interruptible AI reasoning, fine-grained bidirectional dialogue, and a shared cognitive context. At the core of our system is a layered StateManager architecture and a novel multi-stage budget allocation algorithm. This architecture ingests and normalizes all interaction data (e.g., dialogue trajectories and user artifacts) into a perpetually optimized, high-information-density working memory. By dynamically prioritizing context based on a combination of static heuristics and a time-sensitive scoring function, our system mitigates error cascades and allows the AI to adapt its reasoning pathways based on the user's implicit focus. We conduct a comprehensive user study on challenging deep research tasks to evaluate the efficacy of our system. Results show that our approach significantly enhances the user experience, yielding improvements of up to 29.2\% in Fine-Grained Interaction and 27.7\% in Ease of Collaboration compared to a competitive baseline. Most notably, our system demonstrates a 31.8\% to 50.0\% points improvement in overall task performance. These results highlight the critical importance of designing interactive AI systems that facilitate continuous human guidance and transparent reasoning, rather than merely responding to isolated commands.

Chat is not available.